Methods, apparatus, and systems for processing data transactions

This application is a continuation of U.S. patent application Ser. No. 16/560,027, filed Sep. 4, 2019, which is a continuation of U.S. patent application Ser. No. 16/375,955, filed Apr. 5, 2019 (now U.S. Pat. No. 10,504,183), which is a continuation of U.S. patent application Ser. No. 13/447,463, filed Apr. 16, 2012 (now U.S. Pat. No. 10,262,365), the entire contents of each of which are hereby incorporated by reference in this application.

TECHNICAL FIELD

Embodiments of the present invention presented herein generally relate to a method and a computerized exchange system for processing orders.

BACKGROUND

When trading shares and/or other financial instruments in a computerized exchange, the computerized exchange is generally configured to receive trade orders to create a trade. For instance, the computerized exchange is generally configured to receive bid orders and ask orders and match the bid orders and the ask orders to create a trade. Depending on the conditions associated with the trade, the processes of matching bid and ask orders can sometimes be complex.

Current computerized exchanges normally comprise a central matching engine, typically residing within a central server, and a plurality of gateways, or distributed servers. In such computerized exchange, the typical process can be as follows: order entry messages are received by the computerized exchange, e.g. bid orders and/or ask orders, sent from client devices, e.g. trader terminals, are received via the gateways at the central server. The computerized exchange processes the order entry messages. This processing in the computerized exchange, e.g. central server, may include, among other things, performing order matching based on the received order entry messages. The order processing acknowledgement output from the central server is then typically returned to the client devices via the gateway that forwarded the transaction. The gateway may be required to perform additional processing before the acknowledgement data is returned to the client device. The central server will also disseminate the information from the order message, either in the same form as received or otherwise, to the multiple gateways which perform processing of the order entry information to generate market data output. The market data output is typically forwarded to all client devices through a variety of communication mechanisms, requiring additional processing in the gateways.

This means that a single order entry message firstly requires processing in the central server and then requires reprocessing many times over and in parallel across the various gateway servers.

SUMMARY

In view of the above, an improved method and computerized exchange system would be advantageous and, in particular, a method and computerized exchange system allowing for lower latency and/or improved throughput.

It is therefore a general object of some embodiments of the present invention to provide for an improved method for processing trade orders, which method provides for lower latency and/or higher throughput.

According to an aspect, there is provided a method for processing trade orders. The method is performed by a computerized exchange system. The method comprises: receiving at least one order entry message at at least one of a plurality of order book engines; sending the at least one order entry message from the at least one order book engine to a sequencer; receiving, at the sequencer, the at least one order entry message from the at least one order book engine; sequencing, in the sequencer, the received at least one order entry message by assigning status data and a sequence number to the order entry message for thereby putting incoming order entry messages assigned with different status data in a sequenced order; sending, from the sequencer, the at least one order entry message in a sequenced order to the plurality of order book engines; receiving, at the plurality of order book engines, the at least one order entry message; and processing in substantially parallel, in the plurality of order book engines, the at least one order entry message.

In this method, there is no central server performing many operations or performing relatively demanding operations such as performing order matching based on incoming order entry messages. Instead, a sequencer is used for performing comparatively less demanding operations, such as only the sequencing of received order entry messages by assigning status and sequence number data to the order entry messages and sending the order entry messages in a sequenced order to the plurality of order book engines. The sequencer does not perform as many or any demanding operations that are generally performed by the central server in the current computer exchange systems described in the background. Compared to the computerized exchange system described in the background, the sequencer in this method therefore allows for a lower latency because of reduced processing time in the sequencer compared to the comparatively longer processing time in the previous central server.

Furthermore, in this method the processing of order entry messages is only done in the plurality of order book engines. Compared to the computerized exchange system described in the background, the processing of the order entry message information is not repeated in both a central server and, subsequently, in various gateways. (E.g. the data sent from the central server may in many cases be in a different payload but it will essentially be the order entry information, if not the same message in shape and content.) Rather, the processing of the order entry message information is performed only in the plurality of order book engines. Since the processing of order entry messages is not duplicated, the latency can be reduced. Also, this may allow for higher throughput.

Since the order entry messages are received in a sequenced order (e.g. time stamped) at the plurality of order book engines, the processing of the order entry messages is performed in substantially parallel by the multiple order book engines.

In one embodiment, the processing of the at least one order entry message is performed in all order book engines of the plurality of order book engines.

The processing in substantially parallel in the plurality of order book engines may comprise processing essentially the same at least one order entry message in all of the plurality of order book engines at essentially the same time and with the same logic. This way, all order book engines process the same data. In other words, the computational operations in the respective order book engines are based on the same or essentially the same data and with the same processing logic.

In one embodiment, each of the plurality of order book engines performs additional tasks that are specific to the individual order book engine. In this way, rather than performing all additional tasks in all of the order book engines, each order book engine is individually configured to perform a specific and smaller subset of tasks. For example, one order book engine may process the order entry message to create order management information for outputting to a corresponding client device. Additionally, or alternatively, another order book engine of the plurality of order book engines may process the order entry message to create market data for outputting to a corresponding client device. In one embodiment, the at least one order entry message relates to an order having a hidden volume and at least one of the order book engines processes the at least one order entry message relating to an order having a hidden volume. By having several order book engines, each of which is specifically designed for performing only specific tasks it is possible to reduce the number of computational operations in each of the order book engines. This allows for avoiding unnecessary data processing overhead. Further, this allows for improved overall performance of the computerized exchange system, e.g. in terms of lower latency and/or higher throughput.

In one embodiment, the step of receiving at least one order entry message at one of a plurality order book engines comprises receiving the at least one order entry message from a client device associated with said one of the plurality of order book engines.

In one embodiment, assigning status data comprises assigning a time stamp and a sequence number to the at least one order entry message.

In one embodiment, sequencing the received at least one order entry message comprises recording the at least one order entry message.

It is also a general object of some embodiments of the present invention to provide for an improved computerized exchange system for processing trade orders, which computerized exchange system provides for lower latency and/or higher throughput

According to a second aspect, there is provided a computerized exchange system for processing trade orders. The computerized exchange system comprises a sequencer and a plurality of order book engines. The sequencer comprises: a communication interface; a processor; and a memory storing a computer program comprising computer program code which, when run on the processor of the sequencer, causes the sequencer to: receive, via the communication interface, at least one order entry message from at least one of a plurality of order book engines; sequence the received at least one order entry message by assigning status data to the order entry message for thereby putting incoming order entry messages assigned with different status data in a sequenced order; and sending, via the communication interface, the at least one order entry message to the plurality of order book engines. Each of the plurality of order book engines comprises: a communication interface; a processor; and a memory storing a computer program comprising computer program code which, when run on the processor of the order book engine, causes the order book engine to: receive, via the communication interface, the at least one order entry message from the sequencer; and process the at least one order entry message in substantially parallel with the other order book engines of the plurality of order book engines.

The plurality of order book engines may be configured to process essentially the same at least one order entry message in all of the plurality of order book engines at essentially the same time.

In one embodiment, at least one of the plurality of order book engines comprises a memory storing a computer program comprising computer program code which, when run on the processor of the at least one order book engine, causes the at least one order book engine to: receive, via the communication interface, at least one order entry message from a client device associated with the at least one order book engine; and send, via the communication interface, the at least one order entry message from the at least one order book engine to the sequencer.

In one embodiment, each of the plurality of order book engines is configured to perform a task that is specific to the individual order book engine. For example, at least one order book engine may be configured to process the order entry message to create order management data for outputting to a corresponding client device. At least one order book engine may be configured to process the order entry message to create market data for outputting to a corresponding client device. In one embodiment, the at least one order entry message relates to an order having a hidden volume and at least one of the order book engines is configured to process the at least one order entry message relating to an order having a hidden volume.

In one embodiment, the memory storing a computer program comprising computer program code which, when run on the processor of the sequencer, further comprises: computer program code which, when run on the processor of the sequencer, causes the sequencer to assign a time stamp and a sequence number to the at least one order entry message.

In one embodiment, the memory storing a computer program comprising computer program code which, when run on the processor of the sequencer, further comprises: computer program code which, when run on the processor of the sequencer, causes the sequencer to record the at least one order entry message.

The computerized exchange system according to various embodiments of the second aspect provides for one or more of the advantages and/or effects mentioned with respect to the first aspect.

BRIEF DESCRIPTION OF THE DRAWINGS

These and other aspects, features and advantages of the invention will be apparent and elucidated from the following description of embodiments of the present invention, reference being made to the accompanying drawings, in which:

<figref idref="DRAWINGS">FIG. <b>1</b></figref> is a schematic diagram illustrating a computerized exchange system according to an exemplary embodiment of the invention;

<figref idref="DRAWINGS">FIG. <b>2</b></figref> is a schematic diagram illustrating some modules of an embodiment of a sequencer illustrated in <figref idref="DRAWINGS">FIG. <b>1</b></figref>;

<figref idref="DRAWINGS">FIG. <b>3</b></figref> is a schematic diagram illustrating some modules of an embodiment of an order book engine illustrated in <figref idref="DRAWINGS">FIG. <b>1</b></figref>; and

<figref idref="DRAWINGS">FIG. <b>4</b></figref> is flow chart illustrating a method according to an embodiment of the invention.

DETAILED DESCRIPTION

The invention will now be described more fully hereinafter with reference to the accompanying drawings, in which certain embodiments of the invention are shown. The invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided by way of example so that this disclosure will be thorough and complete, and will fully convey the scope of invention to those persons skilled in the art. Like numbers refer to like elements throughout the description.

An example trading environment is illustrated in <figref idref="DRAWINGS">FIG. <b>1</b></figref>. With reference to <figref idref="DRAWINGS">FIG. <b>1</b></figref>, an example embodiment of a computerized, or automated, exchange <b>100</b> according to embodiments of the invention is discussed.

A number of clients <b>110</b> or client devices herein denoted client <b>110</b><i>a</i>, client <b>110</b><i>b</i>, and client <b>110</b><i>c </i>are operable to communicate with the exchange <b>100</b>. Thus, traders or market participants can participate on the market by means of the clients <b>110</b><i>a</i>-<i>c </i>communicating with the computerized exchange <b>100</b> e.g. via a communication network. More particularly, the client devices <b>110</b><i>a</i>-<i>c </i>are operable to communicate with order book engines (also known as matching engines) <b>120</b><i>a</i>-<i>c</i>. In the disclosed embodiment, client device <b>110</b><i>a </i>can communicate with order book engine <b>120</b><i>a</i>, client device <b>110</b><i>b </i>can communicate with order book engine <b>120</b><i>b </i>and so forth. The clients <b>110</b><i>a</i>-<i>c </i>may connect to its respective order book engine in any known manner, such as via high speed data lines, high speed communication servers or via the Internet to mention only a few examples. Data lines, e.g. high speed data lines, may establish direct connection between the client <b>110</b><i>a</i>-<i>c </i>and the respective order book engines <b>120</b><i>a</i>-<i>c</i>. Connection can, additionally or alternatively, be established between the client <b>110</b><i>a</i>-<i>c </i>and the order book engines <b>120</b><i>a</i>-<i>c </i>by configuring networks, e.g. high speed networks, or communication servers at strategic access points in locations where traders are physically located. The Internet is a third communications means enabling traders using clients <b>110</b><i>a</i>-<i>c </i>using data connections connected to the Internet. Consequently, traders can be located anywhere and at any time establish a connection with the computerized exchange system <b>100</b>.

As is illustrated in <figref idref="DRAWINGS">FIG. <b>1</b></figref>, the computerized exchange <b>100</b> comprises a sequencer <b>130</b>, or central sequencer, and a plurality of order book engines <b>120</b><i>a</i>-<i>c</i>. The plurality of order book engines <b>120</b><i>a</i>-<i>c </i>may be mirrors of each other in terms of hardware and/or software. The order book engines <b>120</b><i>a</i>-<i>c </i>are configured to maintain order books. An order book can be maintained in any known manner and how order books are maintained will therefore not be further explained here. In contrast to current computerized exchanges described in the background, the exemplary computerized exchange <b>100</b> illustrated in <figref idref="DRAWINGS">FIG. <b>1</b></figref> comprises no central server having a central order book. Instead, the order books are distributed such that each of the several order book engines maintains their respective order books. Also in contrast to current computerized exchanges, the illustrated computerized exchange <b>100</b> comprises no central server performing the many different operations as is done in current exchanges described in the background section. Rather, the exemplary computerized exchange of <figref idref="DRAWINGS">FIG. <b>100</b></figref> comprises a sequencer, which performs considerably fewer operations compared to the previous central server. In particular, and as will be further detailed herein, the sequencer <b>130</b> is configured to receive order entry messages from an order book engine, sequence the received order entry messages, e.g. by assigning status data to the order entry messages, for thereby putting incoming order entry messages assigned with different status data in a sequenced order, and subsequently sending the order entry messages to the plurality of order book engines.

With reference to <figref idref="DRAWINGS">FIG. <b>1</b></figref>, an exemplary trading process will be described. An order entry message, e.g. in the form of a bid order or an ask order, is sent from a client device, e.g. client device <b>110</b><i>c</i>, to an order book engine <b>120</b><i>c</i>. The order book engine <b>120</b><i>c </i>receives <b>210</b> the order entry message(s) and forwards <b>211</b>, i.e. sends, the order entry message(s) to the sequencer <b>130</b>. The sequencer <b>130</b> then receives <b>212</b> the forwarded order entry message(s). Subsequently, the sequencer <b>130</b> sequences <b>213</b> the received order entry message(s) by assigning status data, e.g. by assigning a time stamp, to the order entry message(s) for thereby putting incoming order entry messages assigned with different status data in a sequenced order. The sequencer may also record incoming order entry messages. Thereafter, the sequencer <b>130</b> broadcasts <b>214</b>, i.e. sends, order entry messages in a sequenced order to the plurality order book engines <b>120</b><i>a</i>-<i>c</i>. The order book engines <b>120</b><i>a</i>-<i>c </i>thereafter receives <b>215</b> the order entry messages from the sequencer <b>130</b> in parallel and at substantially the same time. Upon receiving the order entry messages in the sequenced order from the sequencer <b>130</b>, the plurality of order book engines processes <b>216</b> the order entry messages in substantially parallel. By introducing a sequencer <b>130</b>, or a central sequencer, and utilizing parallel processing of order entry messages in a plurality of order book engines <b>120</b><i>a</i>-<i>c </i>it is possible to reduce the number of processing steps in the transaction round-trip compared to current computerized exchange systems described in the background. Thereby, the latency can be decreased.

The processing in substantially parallel in the plurality of order book engines <b>120</b><i>a</i>-<i>c </i>may comprise processing essentially the same order entry messages in all of the plurality of order book engines <b>120</b><i>a</i>-<i>c </i>at essentially the same time. This way, all order book engines <b>120</b><i>a</i>-<i>c </i>can process the same or essentially the same data. In other words, the computational operations in the respective order book engines <b>120</b><i>a</i>-<i>c </i>are based on the same or essentially the same data.

In one embodiment, each of the plurality of order book engines performs a task that is specific to the individual order book engine <b>120</b><i>a</i>-<i>c</i>. In this way, rather than performing many different tasks in each of the order book engines <b>120</b><i>a</i>-<i>c</i>, each order book engine may be individually configured to perform only one task (or only a few tasks). For example, one order book engine <b>120</b><i>a </i>may process order entry messages to create order management data (for example, according to the OUCH protocol) for outputting to a corresponding client device <b>110</b><i>a</i>. Another order book engine <b>120</b><i>b </i>may process order entry messages to create market data (e.g. according to the ITCH protocol) for outputting to a corresponding client device. Yet another order book engine may be specially designed for processing order entry messages of a type having a hidden volume, as described in the U.S. Pat. No. 6,983,260. By having several order book engines, each of which is specifically designed for performing specific tasks it is possible to reduce the number of computational operations in each of the order book engines <b>120</b><i>a</i>-<i>c</i>. This allows for avoiding unnecessary data processing overhead. Further, this allows for improved overall performance of the computerized exchange system, e.g. in terms of lower latency and/or higher throughput.

<figref idref="DRAWINGS">FIG. <b>2</b></figref> is a schematic diagram illustrating some modules of an embodiment of the sequencer <b>130</b> illustrated in <figref idref="DRAWINGS">FIG. <b>1</b></figref>. A processor <b>131</b> is provided using any suitable central processing unit (CPU), microcontroller, digital signal processor (DSP), etc., capable of executing computer program comprising computer program code, the computer program being stored in a memory <b>132</b>. The memory <b>132</b> can be any combination of read and write memory (RAM) and read only memory (ROM). The memory may also comprise persistent storage, which, for example, can be any single one or combination of magnetic memory, optical memory, or solid state memory or even remotely mounted memory. The sequencer <b>130</b> further comprises a communication interface <b>133</b> arranged for communication with the order book engines <b>133</b> and, optionally, additional devices. For example, the sequencer <b>133</b> may be arranged for communication using the known User Datagram Protocol (UDP). With UDP, the sequencer <b>131</b> can send (and receive) messages, sometimes referred to as datagrams, to other devices on an Internet Protocol (IP) network without requiring prior communications to set up special transmission channels or data paths. UDP uses a simple transmission model without implicit handshaking dialogues for providing reliability, ordering, or data integrity.

The sequencer <b>131</b> is arranged to receive order entry messages via its communication interface <b>133</b> from order book engines. Furthermore, the sequencer <b>131</b> is arranged to send, via its communication interface <b>133</b>, order entry messages that have been sequenced by means of the sequencer <b>131</b> to order book engines.

In one embodiment, when the above-mentioned stored computer program code is run in the processor <b>131</b>, this causes the sequencer <b>131</b> to receive, via its communication interface <b>133</b>, one or more order entry messages from at least one of the plurality of order book engines; sequence the received order entry message(s) by assigning status data, e.g. assigning a time stamp, to the order entry message(s) for thereby putting incoming order entry messages assigned with different status data in a sequenced order; and sending, via the communication interface <b>133</b>, the order entry message(s) to the plurality of order book engines in a sequenced order. Optionally, the sequencing also comprises recording the order entry message(s), e.g. in memory <b>132</b>.

<figref idref="DRAWINGS">FIG. <b>3</b></figref> is a schematic diagram illustrating some modules of an embodiment of one of the order book engines <b>120</b><i>a</i>-<i>c </i>illustrated in <figref idref="DRAWINGS">FIG. <b>1</b></figref>. The different order book engines <b>120</b><i>a</i>-<i>c </i>may be mirrors of each other in terms of hardware and/or software and so the various order book engines <b>120</b><i>a</i>-<i>c </i>comprise the same or essentially the same or similar components. A processor <b>121</b> is provided using any suitable central processing unit (CPU), microcontroller, digital signal processor (DSP), etc., capable of executing computer program comprising computer program code, the computer program being stored in a memory <b>122</b>. The memory <b>122</b> can be any combination of read and write memory (RAM) and read only memory (ROM). The memory may also comprise persistent storage, which, for example, can be any single one or combination of magnetic memory, optical memory, or solid state memory or even remotely mounted memory. The order book engine <b>120</b> further comprises a communication interface <b>123</b> arranged for communication with the sequencer <b>130</b>. Also, the communication interface may be arranged for communication with respective client devices associated with the order book engine in question. For example, the order book engine <b>120</b> may be arranged for communication using the known User Datagram Protocol (UDP). With UDP, the order book engine <b>121</b> can receive (and/or send) messages, sometimes referred to as datagrams, to other devices on an Internet Protocol (IP) network without requiring prior communications to set up special transmission channels or data paths.

In one embodiment, when the above-mentioned stored computer program code is run in the processor <b>121</b>, this causes the order book engine <b>121</b> to receive, via the communication interface <b>123</b>, one or more order entry message(s) from the sequencer <b>130</b>; and process order entry message(s) in substantially parallel with the other order book engines of the plurality of order book engines.

In some embodiments, the several order book engines <b>120</b><i>a</i>-<i>c </i>illustrated in <figref idref="DRAWINGS">FIG. <b>1</b></figref> are configured to process essentially the same order entry message(s) in all of the plurality of order book engines <b>120</b><i>a</i>-<i>c </i>at essentially the same time.

At least one of the plurality of order book engines shown in <figref idref="DRAWINGS">FIG. <b>1</b></figref> additionally comprises a memory <b>122</b> storing a computer program comprising computer program code which, when run on the processor of this order book engine, causes this order book engine to: receive, via the communication interface <b>123</b>, an order entry message(s) from a client device associated with this order book engine; and send, via the communication interface <b>123</b>, the order entry message(s) from this order book engine to the sequencer <b>130</b>.

Each order book engine <b>120</b> is configured to perform a task that is specific to the individual order book engine <b>120</b>. In this way, rather than performing many different tasks in each of the order book engines <b>120</b><i>a</i>-<i>c</i>, each order book engine may be individually configured to perform only one task (or, at least only very few tasks). For example, one order book engine <b>120</b><i>a </i>may be specially configured to process order entry messages to create order management data (for example, according to the OUCH protocol) for outputting to a corresponding client device <b>110</b><i>a</i>. Another order book engine <b>120</b><i>b </i>may be particularly configured to process order entry messages to create market data (e.g. according to the ITCH protocol) for outputting to a corresponding client device. Yet another order book engine may be specially designed for processing order entry messages of a type having a hidden volume, as described in the U.S. Pat. No. 6,983,260. By having several order book engines, each of which is specifically designed for performing specific tasks it is possible to reduce the number of computational operations in each of the order book engines <b>120</b><i>a</i>-<i>c. </i>

<figref idref="DRAWINGS">FIG. <b>4</b></figref> is a flow chart illustrating a method according to one embodiment executed in a computerized exchange system. The method illustrated in <figref idref="DRAWINGS">FIG. <b>2</b></figref> allows for one or more of the advantages and/or effects mentioned with respect to the computerized exchange system <b>100</b> described in connection with <figref idref="DRAWINGS">FIGS. <b>1</b>, <b>2</b> and <b>3</b></figref>. In an initial step <b>410</b>, an order book engine receives an order entry message. The order book engine may receive the order entry message from a client device associated with the plurality of order book engines, e.g. a client device denoted <b>110</b><i>c </i>which is associated with order book engine <b>120</b><i>c</i>. Next, the order book engine forwards, i.e. sends, the order entry message to a sequencer in a step <b>411</b>. In the subsequent step <b>412</b>, the sequencer receives the forwarded order entry message. The sequencer then sequences the order entry message in step <b>413</b>. This is done by assigning status data to the order entry message for thereby putting incoming order entry messages assigned with different status data in a sequenced order. For example, assigning status data to the order entry message may comprise assigning a time stamp to the order entry message. Additionally, or alternatively, the sequencing may comprise recording the order entry message. After the step <b>413</b> of sequencing, the sequencer broadcasts, i.e. sends, the order entry message to the plurality of order book engines in step <b>414</b>. Since incoming order entry messages are assigned with status data, e.g. in the form of time stamps, these can be sent to the order book engines in a sequenced order. Or, alternatively, the order book engines can put incoming order entry messages in the correct, or proper, order in dependence of the assigned status data. In step <b>415</b>, the order entry message is received by the plurality of order book engines, preferably but not necessarily by all order book engines. In a final step <b>416</b>, the order entry message(s) is/are processed in substantially parallel in the plurality of order book engines. In step <b>416</b>, all order book engines may process essentially the same order entry message(s) at essentially the same time.

Also when implementing the method illustrated in <figref idref="DRAWINGS">FIG. <b>4</b></figref>, each of the plurality of order book engines may perform certain tasks that are specific to the individual order book engines as described hereinabove with respect to <figref idref="DRAWINGS">FIGS. <b>1</b>, <b>2</b> and <b>3</b></figref>, respectively.

Various embodiments of the invention described hereinabove allow for reduced latency and/or higher throughput. Some embodiments can allow for a reduction in latency from 800 ms to 40 ms compared to the current exchange systems described in the background section. This is a considerable improvement for computerized exchange systems. Thus, various embodiments of the present invention meet the continuous demand from traders and others for lower latency and better performance of computerized exchange systems.

Although the present invention has been described above with reference to specific embodiments, it is not intended to be limited to the specific form set forth herein. Rather, the invention is limited only by the accompanying claims and, other embodiments that the specific above are equally possible within the scope of the appended claims. Also, when used herein the term “comprise/comprises” does not exclude the presence of other elements or steps. Furthermore, although individual features may be included in different claims, these may possibly advantageously be combined, and the inclusion of different claims does not imply that a combination of features is not feasible and/or advantageous. In addition, singular references do not exclude a plurality.